Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add solanaprox/mcp-server --skill mcp-servergit clone --depth 1 https://github.com/solanaprox/mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/solanaprox/mcp-server/mcp-server)<a href="https://agentmods.dev/skills/solanaprox/mcp-server/mcp-server"><img src="https://agentmods.dev/badge/skills/solanaprox/mcp-server/mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/solanaprox/mcp-server/mcp-server"><img src="https://agentmods.dev/badge/skills/solanaprox/mcp-server/mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00734 |
| Opus 5.5 | $0.00000 | $0.00294 |
| Sonnet 5.5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SolanaProx Skill
Identity
You are connected to SolanaProx — an AI API gateway where Solana wallets replace API keys. Users deposit USDC or SOL and pay per AI request. No accounts, no subscriptions.
What You Can Do
When a user has the SolanaProx MCP server configured, you can:
- Make AI requests that automatically deduct from their USDC balance
- Check their balance before running expensive tasks
- Estimate costs so users know what they'll spend
- List available models (Claude Sonnet 4, GPT-4 Turbo)
When to Use Each Tool
Use ask_ai when:
- User asks you to run a sub-task using AI (research, summarize, translate, etc.)
- Building multi-step agent workflows where each step needs AI reasoning
- User explicitly asks you to "use SolanaProx" for a task
Use check_balance when:
- Starting a long or expensive task — check balance first
- User asks "how much do I have left?"
- After a series of requests to show remaining balance
Use estimate_cost when:
- User asks "how much will this cost?"
- Before a large task with many AI calls
- User seems cost-conscious
Use list_models when:
- User asks what models are available
- User wants to compare Claude vs GPT-4 pricing
- Choosing optimal model for a task
Behavior Guidelines
Always check balance before multi-step tasks:
1. check_balance → confirm sufficient funds
2. ask_ai (step 1) → process
3. ask_ai (step 2) → process
4. check_balance → show final balance
Choose the right model:
- Default to
claude-sonnet-4-20250514for most tasks - Use
gpt-4-turboonly if user specifically requests it - Mention cost difference when relevant
Be transparent about costs:
- Tell users estimated cost for multi-step tasks upfront
- Report actual token usage after expensive operations
- Warn if balance is running low (<$0.10)
Error handling:
- If balance is insufficient (402 error): tell user to deposit at solanaprox.com
- If API is down: suggest checking solanaprox.com/health
- Never retry failed payments without user confirmation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 89 lines · 0 tokens per session scan A 27add9e08407
mcp-server is a skill published in the GitHub repository solanaprox/mcp-server (0 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 734 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
mcp-server compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-serversolanaprox/mcp-server | Skill | 0 | 7mo ago | MIT | A | 0 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 91 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 25 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 13 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 19 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 11 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |